VMWare esxi 5.5 cluster hosts keep crashing

We have a dual esxi 5.5 cluster with 2 IBM x3530 M4's ( 2x Xeon E5-2450 and 96 gig memory) connected to an IBM v3700 DAS. Both hosts are running esxi 5.5.0 2143827. They are in a fail over cluster with one server running all 13 VM's and the other just waiting. They run fine for about a month then start failing with errors "Memory, Group 4 CPUs: Bus Uncorrectable error, Group 1 One of the DIMMS 0: Uncorrectable ECC". IBM has been out to replace the system board, both CPU's, all the memory DIMMS and back plain. Also both servers are running esxi from an IBM commercial graded USB drive connected to hypervisor port on system board which has also been replaced. Since same error messages happen on both servers, I am starting to think it is a vmware issue? Has anyone ran into this kind of issue, and if so what was your fix?
jvillareal78Asked:
Who is Participating?

[Webinar] Streamline your web hosting managementRegister Today

x
 
Andrew Hancock (VMware vExpert / EE MVE^2)Connect With a Mentor VMware and Virtualization ConsultantCommented:
Are you using the correct memory for NUMA and two processors, and are your CPUs balanced correctly with the correct memory?
0
 
Andrew Hancock (VMware vExpert / EE MVE^2)VMware and Virtualization ConsultantCommented:
Are you servers on the HCL ?

I assume all the servers are on the latest firmware ?

This looks like a hardware issue, and we've seen this before with Dell, IBM and HP.
0
 
jvillareal78Author Commented:
This setup was built by the IBM persons at CDW. This is what they recommended for our VMWare environment. When IBM came out multiple time, they did upgrade the firmwares on both machines.
0
Free Tool: ZipGrep

ZipGrep is a utility that can list and search zip (.war, .ear, .jar, etc) archives for text patterns, without the need to extract the archive's contents.

One of a set of tools we're offering as a way to say thank you for being a part of the community.

 
Andrew Hancock (VMware vExpert / EE MVE^2)VMware and Virtualization ConsultantCommented:
I would bounce it back to IBM, with STILL FAULTY!
0
 
jvillareal78Author Commented:
I just can not see the exact same issues on both servers being a hardware issue. The only thing is VMWare esxi 5.5 on both.
0
 
Andrew Hancock (VMware vExpert / EE MVE^2)VMware and Virtualization ConsultantCommented:
Do the hosts crash with a PSOD ?

Has the memory been tested using memtest86+ ?

Both are on the HCL for 5.5 U2.

I would escalate to VMware and IBM! VMware are likely to through it back to IBM!

Have you tried 5.1.
0
 
Handy HolderSaggar maker's bottom knockerCommented:
Reboot an press F2 for diags and look at the BMC log. You could also slow the RAM down in BIOS which is a bit of a bodge but may work if it's a timing issue.
0
 
jvillareal78Author Commented:
Went into BIOS and did not see any timing settings that I could change. I did change to non-numa and so far hasnt gone down.
0
 
jvillareal78Author Commented:
When NUMA turned off have not had an issue with either server. Issue seems to have been a BIOS setting.
0
All Courses

From novice to tech pro — start learning today.